Confounding

Question 1

In the design stage (Jager, 2008) of an experiment, confounding can be controlled by:

Answer 1

randomisation (which aims to produce an even amount of potential risk factors in two populations.
restriction (For example, in a study looking at the association between physical activity and heart disease, suppose that age and gender are the only two confounders of concern. If so, confounding by these factors could be avoided by making sure that all subjects are males between the ages of 40-50. This will ensure that the age distributions are similar in the groups being compared, so that confounding will be minimised)
matching (This is active form of control. For example, to ensure that two study groups do not differ with respect to possible confounders such as age and gender for every active male between the ages of 40-50, we could find and enroll an inactive male between the ages of 40-50. In this way, the groups we are comparing can artificially be made similar with respect to these factors, so they cannot confound the relationship).

Question 2

In the analysis stage (Pourhoseingholi, 2012) of an experiment, confounding can be controlled for by:

Answer 2

stratification
multivariate models (e.g. logistic regression, linear regression, analysis of covariance (ANCOVA))